# Stack Overflow [machine-learning]: Why not use only non-missing value rows as the test set when evaluating an imputed ML pipeline? — retained record

> Retained stackexchange record from stackexchange.

Canonical: https://highsignal.app/data/records/38012a3fcc2fdbf4

[← sources](https://highsignal.app/data)


source: [stackexchange](https://highsignal.app/data/stackexchange) published 2026-06-30 20:00 ingested 2026-07-01 09:37

[original source ↗](https://stackoverflow.com/questions/79971881/why-not-use-only-non-missing-value-rows-as-the-test-set-when-evaluating-an-imput)

## retained text



```
Score: 1 | Answers: 2 | Views: 64
Tags: python, machine-learning, missing-data, imputation
Why not use only non-missing value rows as the test set when evaluating an imputed ML pipeline?
```



document fetched 2026-07-30 08:13
